Piening, Moritz;
Altekrüger, Fabian;
Hertrich, Johannes;
Hagemann, Paul;
Walther, Andrea;
Steidl, Gabriele;
(2024)
Learning from small data sets: Patch‐based regularizers in inverse problems for image reconstruction.
GAMM-Mitteilungen
, Article e202470002. 10.1002/gamm.202470002.
(In press).
Preview |
Text
GAMM.pdf - Published Version Download (27MB) | Preview |
Abstract
The solution of inverse problems is of fundamental interest in medical and astronomical imaging, geophysics as well as engineering and life sciences. Recent advances were made by using methods from machine learning, in particular deep neural networks. Most of these methods require a huge amount of data and computer capacity to train the networks, which often may not be available. Our paper addresses the issue of learning from small data sets by taking patches of very few images into account. We focus on the combination of model‐based and data‐driven methods by approximating just the image prior, also known as regularizer in the variational model. We review two methodically different approaches, namely optimizing the maximum log‐likelihood of the patch distribution, and penalizing Wasserstein‐like discrepancies of whole empirical patch distributions. From the point of view of Bayesian inverse problems, we show how we can achieve uncertainty quantification by approximating the posterior using Langevin Monte Carlo methods. We demonstrate the power of the methods in computed tomography, image super‐resolution, and inpainting. Indeed, the approach provides also high‐quality results in zero‐shot super‐resolution, where only a low‐resolution image is available. The article is accompanied by a GitHub repository containing implementations of all methods as well as data examples so that the reader can get their own insight into the performance.
| Type: | Article |
|---|---|
| Title: | Learning from small data sets: Patch‐based regularizers in inverse problems for image reconstruction |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1002/gamm.202470002 |
| Publisher version: | https://doi.org/10.1002/gamm.202470002 |
| Language: | English |
| Additional information: | © 2024 The Authors. GAMM-Mitteilungen published by Wiley-VCH GmbH. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
| Keywords: | Computed tomography, generative neural networks, inpainting, inverse problems, Langevin Monte Carlo Sampling, small data sets, super-resolution, uncertainty quantification, Wasserstein distances, zero-shot learning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10195704 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
